Show simple item record

dc.contributor.authorElshazly, Hatem Mohamed Abdelfattah Eid
dc.contributor.authorLordan Gomis, Francesc
dc.contributor.authorEjarque Artigas, Jorge
dc.contributor.authorBadia Sala, Rosa Maria
dc.contributor.otherUniversitat Politècnica de Catalunya. Doctorat en Arquitectura de Computadors
dc.contributor.otherUniversitat Politècnica de Catalunya. Departament d'Arquitectura de Computadors
dc.contributor.otherBarcelona Supercomputing Center
dc.date.accessioned2021-03-10T10:37:15Z
dc.date.available2021-03-10T10:37:15Z
dc.date.issued2021-07-01
dc.identifier.citationElshazly, H. [et al.]. Accelerated execution via eager-release of dependencies in task-based workflows. "The international journal of high performance computing applications (IJHPCA)", 1 Juliol 2021, vol.35, núm. 4, p. 325-343
dc.identifier.issn1094-3420
dc.identifier.urihttp://hdl.handle.net/2117/341363
dc.description.abstractTask-based programming models offer a flexible way to express the unstructured parallelism patterns of nowadays complex applications. This expressive capability is required to achieve maximum possible performance for applications that are executed in distributed execution platforms. In current task-based workflows, tasks are launched for execution when their data dependencies are satisfied. However, even though the data dependencies of a certain task might have been already produced, the execution of this task will be delayed until its predecessor tasks completely finish their execution. As a consequence of this approach of releasing dependencies, the amount of parallelism inherent in applications is limited and performance improvement opportunities are wasted. To mitigate this limitation, we propose an eager approach for releasing data dependencies. Following this approach, the execution of tasks will not be delayed until their predecessor tasks completely finish their execution, instead, tasks will be launched for execution as soon as their data requirements are available. Hence, more parallelism is exposed and applications can achieve higher levels of performance by overlapping the execution of tasks. Towards achieving this goal, in this paper we propose applying two changes to task-based workflow systems. First, modifying the dependency relationships of tasks to be specified not only in terms of predecessor and successor tasks but also in terms of the data that caused these dependencies. Second, triggering the release of dependencies as soon as a predecessor task generates the output data instead of having to wait until the end of the predecessor execution to release all of its dependencies. We realize this proposal using PyCOMPSs: a task-based programming model for parallelizing Python applications. Our experiments show that using an eager approach for releasing dependencies achieves more than 50% performance improvement in the total execution time as compared to the default approach of releasing dependencies.
dc.description.sponsorshipThis work is partially supported by the European Union through the Horizon 2020 research and innovation programme under contracts 721865 (EXPERTISE Project) by the Spanish Government (SEV2015-0493,TIN2015-65316-P) and the Generalitat de Catalunya (contract 2014-SGR1051).
dc.language.isoeng
dc.publisherSage
dc.subjectÀrees temàtiques de la UPC::Informàtica::Arquitectura de computadors
dc.subject.lcshHigh performance computing
dc.subject.lcshParallel programming (Computer science)
dc.subject.otherTask-based workflows
dc.subject.otherPartial dependencies
dc.subject.otherLazy dependency release
dc.subject.otherEager dependency release
dc.subject.otherDistributed execution
dc.titleAccelerated execution via eager-release of dependencies in task-based workflows
dc.typeArticle
dc.subject.lemacCàlcul intensiu (Informàtica)
dc.subject.lemacProgramació en paral·lel (Informàtica)
dc.contributor.groupUniversitat Politècnica de Catalunya. CAP - Grup de Computació d'Altes Prestacions
dc.identifier.doi10.1177/1094342021997558
dc.description.peerreviewedPeer Reviewed
dc.relation.publisherversionhttps://journals.sagepub.com/doi/abs/10.1177/1094342021997558
dc.rights.accessOpen Access
local.identifier.drac30736100
dc.description.versionPostprint (author's final draft)
dc.relation.projectidinfo:eu-repo/grantAgreement/MINECO//TIN2015-65316-P/ES/COMPUTACION DE ALTAS PRESTACIONES VII/
dc.relation.projectidinfo:eu-repo/grantAgreement/AGAUR/V PRI/2014 SGR 1051
dc.relation.projectidinfo:eu-repo/grantAgreement/EC/H2020/721865/EU/models, EXperiments and high PERformance computing for Turbine mechanical Integrity and Structural dynamics in Europe/EXPERTISE
local.citation.authorElshazly, H.; Lordan, F.; Ejarque, J.; Badia, R.M.
local.citation.publicationNameThe international journal of high performance computing applications (IJHPCA)
local.citation.volume35
local.citation.number4
local.citation.startingPage325
local.citation.endingPage343


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record